One outstanding challenge for machine learning in diagnostic biomedical imaging is algorithm interpretability. A key application is the identification of subtle epileptogenic focal cortical dysplasias (FCDs) from structural MRI. FCDs are difficult to visualize on structural MRI but are often amenable to surgical resection. We aimed to develop an open-source, interpretable, surface-based machine-learning algorithm to automatically identify FCDs on heterogeneous structural MRI data from epilepsy surgery centres worldwide. The Multi-centre Epilepsy Lesion Detection (MELD) Project collated and harmonized a retrospective MRI cohort of 1015 participants, 618 patients with focal FCD-related epilepsy and 397 controls, from 22 epilepsy centres worldwide. We created a neural network for FCD detection based on 33 surface-based features. The network was trained and cross-validated on 50% of the total cohort and tested on the remaining 50% as well as on 2 independent test sites. Multidimensional feature analysis and integrated gradient saliencies were used to interrogate network performance. Our pipeline outputs individual patient reports, which identify the location of predicted lesions, alongside their imaging features and relative saliency to the classifier. On a restricted ‘gold-standard’ subcohort of seizure-free patients with FCD type IIB who had T1 and fluid-attenuated inversion recovery MRI data, the MELD FCD surface-based algorithm had a sensitivity of 85%. Across the entire withheld test cohort the sensitivity was 59% and specificity was 54%. After including a border zone around lesions, to account for uncertainty around the borders of manually delineated lesion masks, the sensitivity was 67%. This multicentre, multinational study with open access protocols and code has developed a robust and interpretable machine-learning algorithm for automated detection of focal cortical dysplasias, giving physicians greater confidence in the identification of subtle MRI lesions in individuals with epilepsy.

中文翻译：

---

可解释的局灶性皮质发育不良表面检测：多中心癫痫病灶检测研究


诊断生物医学成像中的机器学习面临的一项突出挑战是算法的可解释性。一个关键应用是从结构 MRI 中识别细微的致癫痫性局灶性皮质发育不良 (FCD)。 FCD 很难在结构 MRI 上可视化，但通常可以通过手术切除。我们的目标是开发一种开源、可解释、基于表面的机器学习算法，以根据来自全球癫痫手术中心的异构结构 MRI 数据自动识别 FCD。多中心癫痫病灶检测 (MELD) 项目整理并协调了来自全球 22 个癫痫中心的 1015 名参与者、618 名局灶性 FCD 相关癫痫患者和 397 名对照者的回顾性 MRI 队列。我们创建了一个基于 33 个表面特征的 FCD 检测神经网络。该网络在总队列中的 50% 上进行了训练和交叉验证，并在其余 50% 上以及 2 个独立测试站点上进行了测试。使用多维特征分析和集成梯度显着性来询问网络性能。我们的管道输出个体患者报告，该报告识别预测病变的位置，以及它们的成像特征和对分类器的相对显着性。在具有 T1 和液体衰减反转恢复 MRI 数据的无癫痫发作的 IIB 型 FCD 患者的限制“金标准”子队列中，基于 MELD FCD 表面的算法的灵敏度为 85%。在整个保留测试队列中，敏感性为 59%，特异性为 54%。在包括病灶周围的边界区域后，为了解决手动描绘的病灶掩模边界周围的不确定性，灵敏度为 67%。 这项采用开放访问协议和代码的多中心、跨国研究开发了一种强大且可解释的机器学习算法，用于自动检测局灶性皮质发育不良，使医生更有信心识别癫痫患者的细微 MRI 病变。