You probably don’t think much about medical scan data. But they’re everywhere. If you’ve got an X-ray or an MRI, your images were almost certainly processed by DICOM (Digital Imaging and Communications in Medicine), the globally accepted standard for storing and sharing medical imaging data like X-rays, MRIs, and CT scans between hospitals, clinics, and research institutions since the late 80s and early 90s. But there’s a problem: while medical technology has made incredible leaps in the last 30 years, DICOM hasn’t kept up. What is DICOM anyway? DICOM still operates in ways that feel more suited to a 1990s environment of local networks and limited computing power. Despite updates, the system doesn’t meet the demands of cloud computing, AI-driven diagnostics, and real-time collaboration. It lacks cloud-native support and rigid file structures, and shows inconsistencies between different manufacturers. If your doctor still hands you a CD with your scan on it in 2025 (!), DICOM is a big part of that story. The DICOM Legacy How DICOM Came to Be When DICOM was developed in the 1980s, the focus was on solving some big problems in medical imaging, and honestly, it did the job brilliantly for its time. The initial idea was to create a universal language for different hardware and software platforms to communicate with each other, sort of like building a shared language for technology. They also had to make sure it was compatible with older devices already in use. At that time, the most practical option was to rely on local networks since cloud-based solutions simply didn’t exist yet. These decisions helped DICOM become the go-to standard, but they also locked it into an outdated framework that’s now tough to update. Why It’s Hard to Change DICOM Medical standards don’t evolve as fast as consumer technology like phones or computers. Changing something like DICOM doesn’t happen overnight. It’s a slow and complicated process muddled by layers of regulatory approvals and opinions from a tangled web or organizations and stakeholders. What’s more, hospitals have decades of patient data tied to these systems, and making big changes that may break compatibility isn’t easy. And to top it all off, device manufacturers have different ways of interpreting and implementing DICOM, so it’s nearly impossible to enforce consistency. The Trouble With Staying Backwards Compatible DICOM’s focus on working perfectly with old systems was smart at the time, but it’s created some long-term problems. Technological advancements have moved on with AI, cloud storage, and tools for real-time diagnostics. They have shown immediately how limited DICOM can be in catching up with these innovations. Also, vendor-specific implementations have created quirks that make devices less compatible with one another than they should be. And don’t even get started on trying to link DICOM with modern healthcare systems like electronic records or telemedicine platforms. It would be like trying to plug a 1980s gadget into a smart technology ecosystem — not impossible, but far from seamless. Why Your CT Scanner and MRI Machine Aren’t Speaking the Same Language Interoperability in medical imaging sounds great in theory — everything just works, no matter the device or manufacturer — however, in practice, things got messy. Some issues sound abstract, but for doctors and hospitals, they mean delays, misinterpretations, and extra burden. So, why don’t devices always play nice? The Problem With “Standards” That Aren’t Very Standard You’d think having a universal standard like DICOM would ensure easy interoperability because everybody follows the same rules. Not exactly. Device manufacturers implement it differently, and this leads to: Private tags. These are proprietary pieces of data that only specific software can understand. If your software doesn’t understand them, you’re out of luck. Missing or vague fields. Some devices leave out crucial metadata or define it differently. File structure issues. Small differences in how data is formatted sometimes make files unreadable. The idea of a universal standard is nice, but the way it’s applied leaves a lot to be desired. Metadata and Tag Interpretation Issues DICOM images contain extensive metadata to describe details like how the patient was positioned during the scan or how the images fit together. But when this metadata isn’t standardized, you end up with metadata and tag interpretation issues. For example, inconsistencies in slice spacing or image order can throw off 3D reconstructions, leaving scans misaligned. As a result, when doctors try to compare scans over time or across different systems, they often have to deal with mismatched or incomplete data. These inconsistencies make what should be straightforward tasks unnecessarily complicated and create challenges for accurate diagnoses and proper patient care. File Structure and Storage Inconsistencies The way images are stored varies so much between devices that it often causes problems. Some scanners save each image slice separately. Others put them together in one file. Then there are slight differences in DICOM implementations that make it difficult to read images on some systems. Compression adds another layer of complexity — it’s not the same across the board. File sizes and levels of quality vary widely. All these mismatches and inconsistencies make everything harder for hospitals and doctors trying to work together. Orientation and Interpretation Issues Medical imaging is incredible, but sometimes working with scans slows things down when time matters most and makes it harder to get accurate insights for patient care. There are several reasons for this. Different Coordinate Systems Sometimes, DICOM permits the use of different coordination systems and causes confusions. For instance, patient-based coordinates relate to the patient’s body, like top-to-bottom (head-to-feet) or side-to-side (left-to-right). Scanner-based coordinates, on the other hand, are based on the imaging device itself. When these systems don’t match up, it creates misalignment issues in multi-modal imaging studies, where scans from different devices need to work together. Slice Ordering Problems Scans like MRIs and CTs are made up of thin cross-sectional images called slices. But not every scanner orders or numbers these slices in the same way. Some slices can be stored from top-to-bottom or bottom-to-top. If the order…

Introduction The World of Artificial Intelligence (AI) and Its Application in Content Creation for RPG Games Recently, the world of IT technology has been actively filled with various iterations of artificial intelligence. From advanced chatbots that provide technical support to complex algorithms aiding doctors in disease diagnosis, AI’s presence is increasingly felt. In a few years, it might be hard to imagine our daily activities without artificial intelligence, especially in the IT sector. Let’s focus on generative artificial intelligence, such as TensorFlow, PyTorch, and others, which have long held an important place in software development. However, special attention should be given to the application of AI in the video game industry. We see AI being used from voice generation to real-time responses. Admittedly, this area is not yet so developed as to be widely implemented in commercially available games. But the main emphasis I want to make is on the creation and enhancement of game content using AI. In my opinion, this is the most promising and useful direction for game developers. The Lack of Resources in Creating Large and Ambitious RPG Games and How AI Can Be a Solution In the world of indie game development, a field with which I am closely familiar, the scarcity of resources, especially time and money, is always a foremost challenge. While artificial intelligence (AI) cannot yet generate money or add extra hours to the day (heh-heh), it can be the key to effectively addressing some of these issues. Realism here is crucial. We understand that AI cannot write an engaging story or develop unique gameplay mechanics – these aspects remain the domain of humans (yes, game designers and other creators can breathe easy for now). However, where AI can truly excel is in generating various items, enhancing ideas, writing coherent texts, correcting errors, and similar tasks. With such capabilities, AI can significantly boost the productivity of each member of an indie team, freeing up time for more creative and unique tasks, from content generation to quest structuring. What is Artificial Intelligence and How Can it be Used in Game Development For effective use of AI in game development, a deep understanding of its working principles is essential. Artificial intelligence is primarily based on complex mathematical models and algorithms that enable machines to learn, analyze data, and make decisions based on this data. This could be machine learning, where algorithms learn from data over time becoming more accurate and efficient, or deep learning, which uses neural networks to mimic the human brain. Let’s examine the main types of AI Narrative AI (OpenAI ChatGPT, Google BERT): Capable of generating stories, dialogues, and scripts. Suitable for creating the foundations of the game world and dialogues. Analytical AI (IBM Watson, Palantir Technologies): Focuses on data collection and analysis. Used for optimizing game processes and balance. Creative AI (Adobe Photoshop’s Neural Filters, Runway ML): Able to create visual content such as textures, character models, and environments. Generative AI (OpenAI DALL-E, GPT-3 and GPT-4 from OpenAI): Ideal for generating unique names, item descriptions, quest variability, and other content. By understanding the strengths and weaknesses of each type of AI, developers can use them more effectively in their work. For example, using AI to generate original stories or quests can be challenging, but using it for correcting grammatical errors or generating unique names and item descriptions is more realistic and beneficial. This allows content creators to focus on more creative aspects of development, optimizing their time and resources. An Overview of the Characteristics of Large Fantasy RPG Games and Their Content Requirements In large fantasy RPG games, not only gameplay and concept play a pivotal role, but also the richness and variability of content – spells, quests, items, etc. This diversity encourages players to immerse themselves in the game world, sometimes spending hundreds of hours exploring every nook and cranny. The quantity of this content is important, but so is its quality. Imagine, we offer the player a relic named “Great Heart” with over 100 attribute variations – that’s one approach. But if we offer 100 different relics, each with a unique name and 3-4 variations in description, the player’s experience is significantly different. In AAA projects, the quality of content is usually high, with hundreds of thousands of hours invested in creating items, stories, and worlds. However, in the indie sector, the situation is different: there’s a limited number of items, less variability – unless we talk about roguelikes, where world and item generation are used. A typical feature of roguelikes is the randomization of item attributes. However, they rarely offer unique generation of names or descriptions; if they do, it’s more about applying formulas and substitution rules, rather than AI. This opens new possibilities for the use of artificial intelligence – not just as a means of generating random attributes, but also in creating deep, unique stories, characters, and worlds, adding a new dimension to games. Integrating AI for Item Generation: How AI Can Assist in Creating Unique Items (Clothing, Weapons, Consumables). One of the practical examples of using AI is creating variations based on existing criteria. Why do I consider this the best way to utilize AI? Firstly, having written the story of your game world, we can set limits for the AI, providing clear input and output data. This ensures a 100% predictable outcome from AI. Let’s examine this more closely. When talking about the world’s story, I mean a few pages that describe the world, its nature, and rules. It could be fantasy, sci-fi, with examples of names, unique terminology, or characteristic features that help AI understand the mood and specifics of the world. Here is an excerpt from the text I wrote for my game world. The Kingdom of Arteria is an ancient and mysterious realm, shrouded in secrets and imbued with a powerful form of dark magic. For centuries, it has been ruled by Arteon the First, a wise and just monarch whose benevolence has brought peace and prosperity to his…

Enthusiasts have introduced a remarkable feature that combines Sora’s video-generating capabilities with ElevenLabs’ neural network for sound generation. The result? A mesmerizing fusion of professional 3D locations and lifelike sounds that promises to usher in an era of unparalleled creativity for game developers. How It Works In the context of game development, it should have looked like this: Capture Video with Sora: People start by capturing video content using Sora, a platform known for its advanced video generation capabilities. Luma Neuron Transformation: The captured video is then passed through the Luma neuron. This neural network works its magic, transforming the ordinary footage into a spectacular 3D location with professional finesse. Unity Integration: The transformed video is seamlessly imported into Unity, a widely-used game development engine. Unity’s versatility allows for the integration of the 3D video locations, creating an immersive visual experience that goes beyond the boundaries of traditional content creation. Voilà! The result is nothing short of extraordinary – a unique 3D location ready to captivate audiences and elevate the standards of digital content. A Harmonious Blend of Sights and Sounds But the innovation doesn’t stop there. Thanks to ElevenLabs and its state-of-the-art neural network for sound generation, users can now pair the visually stunning 3D locations with sounds that are virtually indistinguishable from reality. By simply describing the desired sound, the neural network works its magic to create a bespoke audio experience. This perfect synergy between Sora’s visual prowess and ElevenLabs’ sonic wizardry opens up a realm of possibilities for creators, allowing them to craft content that not only looks stunning but sounds authentic and immersive. OpenAI’s Sora & ElevenLabs: How Will They Impact Game Development? The emergence of tools like OpenAI’s Sora and ElevenLabs sparks discussions about their potential impact on the industry. Amidst the ongoing buzz about AI revolutionizing various fields, game developers find themselves at the forefront of this technological wave. However, the reality may not be as revolutionary as some might suggest. Concerns Amidst Excitement: Unraveling the Real Impact of AI Tools in Game Development Today’s AI discussions often echo the same sentiments: fears of job displacement and the idea that traditional roles within game development might become obsolete. Yet, for those entrenched in the day-to-day grind of creating games, the introduction of new tools is seen through a more pragmatic lens. For game developers, the process is straightforward – a new tool is introduced, tested, evaluated, and eventually integrated into the standard development pipeline. AI, including platforms like Sora and ElevenLabs, is perceived as just another tool in the toolkit, akin to game engines, version control systems, or video editing software. Navigating the Practical Integration of AI in Game Development The impact on game development, in practical terms, seems to be more about efficiency and expanded possibilities than a complete overhaul of the industry. Developers anticipate that AI will become part of the routine, allowing for more ambitious and intricate game designs. This shift could potentially lead to larger and more complex game projects, offering creators the time and resources to delve into more intricate aspects of game development. However, there’s a sense of weariness among developers regarding the constant discussion and hype surrounding AI. The sentiment is clear – rather than endlessly discussing the potential far-reaching impacts of AI, developers prefer practical engagement: testing, learning, integrating, and sharing insights on how these tools can be effectively utilized in the real world. OpenAI — for all its superlatives — acknowledges the model isn’t perfect. It writes: “[Sora] may struggle with accurately simulating the physics of a complex scene, and may not understand specific instances of cause and effect. For example, a person might take a bite out of a cookie, but afterward, the cookie may not have a bite mark. The model may also confuse spatial details of a prompt, for example, mixing up left and right, and may struggle with precise descriptions of events that take place over time, like following a specific camera trajectory.” So, AI can’t fully create games and its impact might be limited. While it could serve as a useful tool for quickly visualizing ideas and conveying them to a team, the core aspects of game development still require human ingenuity and creativity. In essence, the introduction of AI tools like Sora and ElevenLabs is seen as a natural progression – a means to enhance efficiency and open doors to new creative possibilities. Rather than a radical transformation, game developers anticipate incorporating AI seamlessly into their workflow, ultimately leading to more expansive and captivating gaming experiences.