[{"data":1,"prerenderedAt":107},["ShallowReactive",2],{"profile":3,"work-diagnostic-vision-models":14},{"name":4,"role":5,"tagline":6,"location":7,"contact":8},"Sankar Vema","AI Builder & Architect of Agentic Systems","I help enterprise leaders turn AI ambition into capability that actually ships.","India · open to global advisory engagements",{"email":9,"linkedin":10,"github":11,"blog":12,"twitter":13},"sankar.vema@gmail.com","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fsankarvema\u002F","http:\u002F\u002Fsankarvema.github.io\u002F","http:\u002F\u002Fsankarvema.blogspot.com\u002F","https:\u002F\u002Ftwitter.com\u002Fsansvema",{"id":15,"title":16,"body":17,"context":79,"description":71,"domain":80,"draft":81,"extension":82,"hero":83,"impact":84,"meta":85,"navigation":86,"path":87,"role":88,"scale":89,"seo":90,"slug":91,"stack":92,"status":97,"stem":98,"tags":99,"year":105,"__hash__":106},"work\u002Fwork\u002Fdiagnostic-vision-models.md","Diagnostic Vision Models for Medicine and Agriculture",{"type":18,"value":19,"toc":70},"minimark",[20,25,29,33,36,40,63,67],[21,22,24],"h2",{"id":23},"the-mandate","The mandate",[26,27,28],"p",{},"I built and fine-tuned deep-learning models for diagnosis across two domains where a\nmissed positive is the expensive error: medical imaging (brain-tumor and skin-cancer\ndetection) and agriculture (plant-disease detection). Different fields, same discipline:\na model whose mistakes have a real-world cost.",[21,30,32],{"id":31},"the-problem","The problem",[26,34,35],{},"Diagnosis from images is a classification problem where the two kinds of error are not\nequal. In tumor and skin-cancer detection a false negative can be a life. In crop-disease\ndetection a missed outbreak can be a season. A model tuned to maximize headline accuracy\nwill happily trade away the exact errors that matter, because the rare, dangerous case is\nunderrepresented in the data. Getting this right is about the loss you optimize and the\ndata you curate, not the size of the network.",[21,37,39],{"id":38},"the-system","The system",[41,42,43,51,57],"ul",{},[44,45,46,50],"li",{},[47,48,49],"strong",{},"Fine-tuned detectors."," Models adapted to each diagnostic task rather than trained from\nscratch, so limited labeled data goes further.",[44,52,53,56],{},[47,54,55],{},"Cost-aware evaluation."," Tuned and measured against the error that hurts, sensitivity to\nthe dangerous class weighted above raw accuracy.",[44,58,59,62],{},[47,60,61],{},"Domain-honest data curation."," Careful handling of class imbalance and edge cases, because\nin diagnosis the rare case is the whole point.",[21,64,66],{"id":65},"what-it-proves","What it proves",[26,68,69],{},"The same engineering discipline moves across medicine and agriculture: understand which\nmistake is unacceptable, then build and evaluate the model around that, not around a\nleaderboard. High-stakes classification is where that discipline shows.",{"title":71,"searchDepth":72,"depth":72,"links":73},"",3,[74,76,77,78],{"id":23,"depth":75,"text":24},2,{"id":31,"depth":75,"text":32},{"id":38,"depth":75,"text":39},{"id":65,"depth":75,"text":66},"Applied ML engagements","industrial-vision",false,"md","Fine-tuned image models for high-stakes diagnosis, from brain-tumor and skin-cancer detection in medical imaging to plant-disease detection across crops.","Fine-tuned detectors for tumors, skin cancer and crop disease",{},true,"\u002Fwork\u002Fdiagnostic-vision-models","ML Architect","Fine-tuned models, high-stakes classification",{"title":16,"description":71},"diagnostic-vision-models",[93,94,95,96],"Deep Learning","Medical Imaging","Model Fine-Tuning","Image Classification","shipped","work\u002Fdiagnostic-vision-models",[100,101,102,103,104],"build","vision","ml","healthcare","agriculture","2022-2023","RbExKqbOdJkrMrS8UFnAOuqb6JSgUdu7uYQNLcM2ZAY",1790601541938]