Flaharty Kendall A, Chandrasekar Vibha, Castillo Irene J, Duong Dat, Ferreira Carlos R, Ledgister Hanchard Suzanna, Hu Ping, Waikel Rebekah L, Rossignol Francis, Introne Wendy J, Solomon Benjamin D
Medical Genomics Unit, Medical Genetics Branch, National Human Genome Research Institute, National Institutes of Health, Bethesda, Maryland, USA.
Human Biochemical Genetics Section, Medical Genetics Branch, National Human Genome Research Institute, National Institutes of Health, Bethesda, Maryland, USA.
J Inherit Metab Dis. 2025 May;48(3):e70042. doi: 10.1002/jimd.70042.
Deep learning (DL) is increasingly used to analyze medical imaging, but is less refined for rare conditions, which require novel pre-processing and analytical approaches. To assess DL in the context of rare diseases, this study focused on alkaptonuria (AKU), a rare disorder that affects the spine and involves other sequelae; treatments include the medication nitisinone. Since assessing x-rays to determine disease severity can be a slow, manual process requiring considerable expertise, this study aimed to determine whether these DL methods could accurately identify overall spine severity at specific regions of the spine and whether patients were receiving nitisinone. DL performance was evaluated versus clinical experts using cervical and lumbar spine radiographs. DL models predicted global severity scores (30-point scale) within 1.72 ± 1.96 points of expert clinician scores for cervical and 2.51 ± 1.96 points for lumbar radiographs. For region-specific metrics, the degrees of narrowing, calcium, and vacuum disc phenomena at each intervertebral space (IVS) were assessed. The model's narrowing scores were within 0.191-0.557 points from clinician scores (6-point scale), calcium was predicted with 78%-90% accuracy (present, absent, or disc fusion), and vacuum disc phenomenon predictions were less consistent (41%-90%). Intriguingly, DL models predicted nitisinone treatment status with 68%-77% accuracy, while expert clinicians appeared unable to discern nitisinone status (51% accuracy) (p = 2.0 × 10). This highlights the potential for DL to augment certain types of clinical assessments in rare disease, as well as identifying occult features like treatment status.
深度学习（DL）越来越多地用于分析医学影像，但对于罕见病的分析还不够精细，因为罕见病需要新颖的预处理和分析方法。为了在罕见病背景下评估深度学习，本研究聚焦于黑尿症（AKU），这是一种影响脊柱并伴有其他后遗症的罕见疾病；治疗方法包括使用药物尼替西农。由于通过评估X光来确定疾病严重程度可能是一个缓慢的手动过程，需要相当多的专业知识，因此本研究旨在确定这些深度学习方法能否准确识别脊柱特定区域的整体脊柱严重程度，以及患者是否正在接受尼替西农治疗。使用颈椎和腰椎X光片，将深度学习的性能与临床专家进行了比较。深度学习模型预测的全球严重程度评分（30分制）与专家临床医生对颈椎X光片的评分相差1.72±1.96分，对腰椎X光片的评分相差2.51±1.96分。对于特定区域的指标，评估了每个椎间隙（IVS）的狭窄程度、钙化情况和真空椎间盘现象。该模型的狭窄评分与临床医生评分（6分制）相差0.191 - 0.557分，钙化预测准确率为78% - 90%（存在、不存在或椎间盘融合），真空椎间盘现象预测的一致性较差（41% - 90%）。有趣的是，深度学习模型预测尼替西农治疗状态的准确率为68% - 77%，而专家临床医生似乎无法辨别尼替西农治疗状态（准确率为51%）（p = 2.0×10）。这凸显了深度学习在罕见病中增强某些类型临床评估的潜力，以及识别如治疗状态等隐匿特征的能力。
