■下颌骨-面部发育不全伴小头畸形(MFDM)是一种罕见的疾病,具有广泛的症状,以颧骨和下颌骨发育不全为特征,小头畸形,耳朵异常。这里,我们旨在描述MFDM患者的外耳表型,并训练基于人工智能(AI)的模型,以区分MFDM耳朵与非综合征控制耳朵(二进制分类),从耳朵对这种情况的主要鉴别诊断(多分类):TreacherCollins(TC),纳格(NAFD)和收费综合征。
■训练集包含1,592张耳朵照片,相当于550名患者。我们提取了48个完全独立于训练集的患者,每个病人每个耳朵只有一张照片。在基于CNN(卷积神经网络)的耳朵检测之后,图像被自动标记。然后进行广义Procrustes分析,以及使用PCA(主成分分析)的降维。主成分被用作极限梯度提升(XGBoost)模型的输入,使用5倍交叉验证进行优化。最后,该模型在独立的验证集上进行了测试.
■我们在1592张耳朵照片上训练了模型,对应于1,296只对照耳朵,105MFDM,33NAFD,70TC和88CHARGE综合征的耳朵。该模型在对照中检测到MFDM的准确度为0.969[0.838-0.999](p<0.001)和AUC(曲线下面积)为0.975(二元分类)。在第一个多级设计中,平衡精度为0.811[0.648-0.920](p=0.002)(MFDM与控制和鉴别诊断)和0.813[0.544-0.960](p=0.003)在第二个多类设计(MFDM与鉴别诊断)。
■这是基于外耳的畸形学中第一个基于AI的综合症检测模型,为当地护理和转诊开辟有希望的临床应用,和专家中心。
UNASSIGNED: Mandibulo-Facial Dysostosis with Microcephaly (MFDM) is a rare disease with a broad spectrum of symptoms, characterized by zygomatic and mandibular hypoplasia, microcephaly, and ear abnormalities. Here, we aimed at describing the external ear phenotype of MFDM patients, and train an Artificial Intelligence (AI)-based model to differentiate MFDM ears from non-syndromic control ears (binary classification), and from ears of the main differential diagnoses of this condition (multi-class classification): Treacher Collins (TC), Nager (NAFD) and CHARGE syndromes.
UNASSIGNED: The training set contained 1,592 ear photographs, corresponding to 550 patients. We extracted 48 patients completely independent of the training set, with only one photograph per ear per patient. After a CNN-(Convolutional Neural Network) based ear detection, the images were automatically landmarked. Generalized Procrustes Analysis was then performed, along with a dimension reduction using PCA (Principal Component Analysis). The principal components were used as inputs in an eXtreme Gradient Boosting (XGBoost) model, optimized using a 5-fold cross-validation. Finally, the model was tested on an independent validation set.
UNASSIGNED: We trained the model on 1,592 ear photographs, corresponding to 1,296 control ears, 105 MFDM, 33 NAFD, 70 TC and 88 CHARGE syndrome ears. The model detected MFDM with an accuracy of 0.969 [0.838-0.999] (p < 0.001) and an AUC (Area Under the Curve) of 0.975 within controls (binary classification). Balanced accuracies were 0.811 [0.648-0.920] (p = 0.002) in a first multiclass design (MFDM vs. controls and differential diagnoses) and 0.813 [0.544-0.960] (p = 0.003) in a second multiclass design (MFDM vs. differential diagnoses).
UNASSIGNED: This is the first AI-based syndrome detection model in
dysmorphology based on the external ear, opening promising clinical applications both for local care and referral, and for expert centers.